Upload 8 files
Browse files- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- trainer_state.json +12 -12
adapter_config.json
CHANGED
@@ -20,10 +20,10 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"k_proj",
|
24 |
-
"o_proj",
|
25 |
"v_proj",
|
26 |
-
"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
"k_proj",
|
|
|
25 |
"v_proj",
|
26 |
+
"o_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 54560368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f7ae94145a7d9d45bfad555abaa683530e58eab28941d65fe8ca5d97352cbd8
|
3 |
size 54560368
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 27612436
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d823a5493bb5bfd77d12f614b2a30284a47069e0725a72824d16a9ab470392e
|
3 |
size 27612436
|
trainer_state.json
CHANGED
@@ -10,32 +10,32 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"grad_norm": 0.
|
14 |
"learning_rate": 0.00020029985007496252,
|
15 |
-
"loss": 0.
|
16 |
"step": 334
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
-
"eval_loss": 0.
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second": 7.
|
23 |
-
"eval_steps_per_second":
|
24 |
"step": 334
|
25 |
},
|
26 |
{
|
27 |
"epoch": 2.0,
|
28 |
-
"grad_norm": 1.
|
29 |
"learning_rate": 0.0,
|
30 |
-
"loss": 0.
|
31 |
"step": 668
|
32 |
},
|
33 |
{
|
34 |
"epoch": 2.0,
|
35 |
-
"eval_loss": 0.
|
36 |
-
"eval_runtime": 18.
|
37 |
-
"eval_samples_per_second": 7.
|
38 |
-
"eval_steps_per_second": 1.
|
39 |
"step": 668
|
40 |
}
|
41 |
],
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"grad_norm": 0.7986670732498169,
|
14 |
"learning_rate": 0.00020029985007496252,
|
15 |
+
"loss": 0.8294,
|
16 |
"step": 334
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
+
"eval_loss": 0.6858757138252258,
|
21 |
+
"eval_runtime": 18.9055,
|
22 |
+
"eval_samples_per_second": 7.881,
|
23 |
+
"eval_steps_per_second": 1.005,
|
24 |
"step": 334
|
25 |
},
|
26 |
{
|
27 |
"epoch": 2.0,
|
28 |
+
"grad_norm": 1.891516089439392,
|
29 |
"learning_rate": 0.0,
|
30 |
+
"loss": 0.6325,
|
31 |
"step": 668
|
32 |
},
|
33 |
{
|
34 |
"epoch": 2.0,
|
35 |
+
"eval_loss": 0.6478394865989685,
|
36 |
+
"eval_runtime": 18.8168,
|
37 |
+
"eval_samples_per_second": 7.918,
|
38 |
+
"eval_steps_per_second": 1.01,
|
39 |
"step": 668
|
40 |
}
|
41 |
],
|